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. 76910
    Prev
    Next
    INDEX
    Explanations

    suffixes

    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
     vaulted
    -0.07
    -Shop
    -0.07
    ову
    -0.07
    vodu
    -0.07
     Tucker
    -0.07
     ham
    -0.07
    Mas
    -0.07
    endl
    -0.07
    -0.07
     tente
    -0.07
    POSITIVE LOGITS
    -than
    0.10
     всего
    0.09
     реал
    0.08
    _than
    0.08
    (notification
    0.08
     plum
    0.08
    kill
    0.08
    _THAN
    0.08
     정도
    0.07
    еку
    0.07
    Activations Density 0.036%

    No Known Activations