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. 104208
    Prev
    Next
    INDEX
    Explanations

    dream

    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
    tta
    -0.08
    ��
    -0.08
     finals
    -0.08
    ading
    -0.07
    APL
    -0.07
    'él
    -0.07
     erhöht
    -0.07
     nego
    -0.07
     verh
    -0.07
    gold
    -0.07
    POSITIVE LOGITS
     saad
    0.08
     hábitos
    0.08
    (pattern
    0.08
     Abraham
    0.08
     penchant
    0.07
    Bars
    0.07
    ია
    0.07
     mune
    0.07
    ulm
    0.07
     proverb
    0.07
    Activations Density 0.008%

    No Known Activations