© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18893
    Prev
    Next
    INDEX
    Explanations

    acquired items

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ainment
    -0.10
     गति
    -0.10
     establecidos
    -0.09
    -established
    -0.09
    etailed
    -0.09
     методов
    -0.08
    ethoden
    -0.08
    baarheid
    -0.08
     учреж
    -0.08
     etabli
    -0.08
    POSITIVE LOGITS
     donated
    0.13
     purchased
    0.12
     stolen
    0.11
     downloaded
    0.11
     shipped
    0.11
     handmade
    0.10
     used
    0.10
     leaked
    0.10
     confisc
    0.10
    購入
    0.10
    Activations Density 0.396%

    No Known Activations