© 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. 23-RESID-POST-AA
    11. 51362
    Prev
    Next
    INDEX
    Explanations

    pret

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     दश
    -0.08
    -mus
    -0.08
     destr
    -0.08
    лігі
    -0.08
     rpt
    -0.08
    र्त
    -0.07
     mus
    -0.07
    र्ति
    -0.07
     �
    -0.07
    مہ
    -0.07
    POSITIVE LOGITS
    entious
    0.18
    ence
    0.14
    zel
    0.14
    reatment
    0.13
    otyping
    0.13
    ension
    0.13
    ends
    0.12
    ended
    0.11
    ax
    0.10
    entions
    0.10
    Activations Density 0.001%

    No Known Activations