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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 1120
    Prev
    Next
    INDEX
    Explanations

    取り

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oblig
    -0.08
     darle
    -0.08
     Quer
    -0.08
     Autos
    -0.07
     spe
    -0.07
     проц
    -0.07
     Sleeping
    -0.07
    autos
    -0.07
     abst
    -0.07
     hat
    -0.07
    POSITIVE LOGITS
    Gross
    0.08
     break
    0.08
     Gross
    0.07
     attract
    0.07
    liament
    0.07
     כ
    0.07
    gross
    0.06
     Presidential
    0.06
    Ax
    0.06
     prism
    0.06
    Activations Density 0.000%

    No Known Activations