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. 9176
    Prev
    Next
    INDEX
    Explanations

    Single point

    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
     Indexed
    -0.08
     relative
    -0.08
     അത
    -0.08
     think
    -0.07
    ROM
    -0.07
     배
    -0.07
    .variant
    -0.07
     notifications
    -0.07
     LM
    -0.07
     ROM
    -0.07
    POSITIVE LOGITS
     cohesive
    0.09
    中央
    0.09
    形成
    0.08
    ায়
    0.08
    统一
    0.08
     વિસ્તારમાં
    0.08
     কেন্দ্র
    0.08
    /div
    0.08
    地点
    0.08
     cnc
    0.08
    Activations Density 0.014%

    No Known Activations