© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 48001
    Prev
    Next
    INDEX
    Explanations

    Non-english or code words

    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
     budete
    -0.09
     يحت
    -0.08
     thật
    -0.08
     prennent
    -0.08
     shumë
    -0.08
     upe
    -0.08
    пай
    -0.07
    pe
    -0.07
     zato
    -0.07
     së
    -0.07
    POSITIVE LOGITS
     funcionando
    0.09
     функ
    0.08
    Spinner
    0.08
     Sever
    0.08
    _function
    0.08
     functional
    0.08
    _FUNCTION
    0.08
     Molina
    0.08
     функция
    0.07
    _Function
    0.07
    Activations Density 0.001%

    No Known Activations