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. 101673
    Prev
    Next
    INDEX
    Explanations

    model answers

    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
    424
    -0.08
     possibly
    -0.07
    -more
    -0.07
    更加
    -0.07
     PRIMARY
    -0.07
    lei
    -0.07
    --------
    -0.07
    Poss
    -0.07
    ,更
    -0.07
     recycled
    -0.07
    POSITIVE LOGITS
     
    0.10
     तुम्ह
    0.09
     kennism
    0.09
     ари
    0.08
     воспольз
    0.08
     계산
    0.08
     actuar
    0.08
     вычис
    0.08
     познаком
    0.08
     στιγ
    0.08
    Activations Density 0.048%

    No Known Activations