Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56272
    Prev
    Next
    INDEX
    Explanations

    multilingual texts

    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
    adra
    -0.08
     VO
    -0.08
     chow
    -0.08
    _FUNCTION
    -0.08
    cad
    -0.07
    374
    -0.07
     veto
    -0.07
     IOS
    -0.07
     press
    -0.07
    loe
    -0.07
    POSITIVE LOGITS
     resemblance
    0.09
     irreversible
    0.08
    失
    0.08
    ebil
    0.08
    ৃষ্টি
    0.08
     Piedra
    0.08
    ayey
    0.07
     desloc
    0.07
     disruptive
    0.07
    运输
    0.07
    Activations Density 0.001%

    No Known Activations