© 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. 11-RESID-POST-AA
    11. 44471
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rd
    -0.08
    repr
    -0.08
    �
    -0.07
    talk
    -0.07
     Dans
    -0.07
     ele
    -0.07
    Think
    -0.07
     yaitu
    -0.07
    elan
    -0.07
     x
    -0.07
    POSITIVE LOGITS
     выяв
    0.10
     approving
    0.10
     выяс
    0.10
     confirming
    0.09
     feststellen
    0.09
     فإذا
    0.09
     ואם
    0.09
    确认
    0.09
     pinpoint
    0.09
     பார்க்க
    0.09
    Activations Density 0.090%

    No Known Activations