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. 285
    Prev
    Next
    INDEX
    Explanations

    to

    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
    unde
    -0.09
     blinking
    -0.08
    stilling
    -0.08
     мая
    -0.08
     mandat
    -0.07
    opita
    -0.07
     TPS
    -0.07
     αντικ
    -0.07
    duğu
    -0.07
     energética
    -0.07
    POSITIVE LOGITS
     �
    0.09
     adel
    0.08
     Freiheit
    0.07
    "'
    0.07
    _keys
    0.07
     lze
    0.07
    _na
    0.07
    注意
    0.07
    keys
    0.07
    籍
    0.07
    Activations Density 0.003%

    No Known Activations