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. 56178
    Prev
    Next
    INDEX
    Explanations

    punctuation and "and"

    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
    ibat
    -0.08
     pupils
    -0.08
     pupil
    -0.08
     barrage
    -0.07
    Indic
    -0.07
    ಿಬ್ಬ
    -0.07
     initials
    -0.07
     ballon
    -0.07
     परेश
    -0.07
    _MOVE
    -0.07
    POSITIVE LOGITS
    观点
    0.09
     انسان
    0.09
     주장
    0.09
     있다는
    0.09
     argues
    0.08
    とも
    0.08
    다는
    0.08
     advocating
    0.08
     människ
    0.08
     অপর
    0.08
    Activations Density 0.394%

    No Known Activations