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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1291
    Prev
    Next
    INDEX
    Explanations

    Punctuation/Special Characters

    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
    owed
    -0.08
     ilo
    -0.07
     homo
    -0.07
    {sub
    -0.07
     HOST
    -0.07
    -learning
    -0.07
     picturesque
    -0.07
     arising
    -0.07
    ော
    -0.07
     레
    -0.07
    POSITIVE LOGITS
    IRS
    0.08
    ikk
    0.08
     XS
    0.07
     Cus
    0.07
    Trades
    0.07
     XF
    0.07
     Foam
    0.07
     IRQ
    0.07
     stik
    0.07
    Parms
    0.07
    Activations Density 0.000%

    No Known Activations