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. 77119
    Prev
    Next
    INDEX
    Explanations

    Challenges, difficulties

    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
    quit
    -0.10
    läuft
    -0.08
    虽
    -0.08
     Giorgio
    -0.08
     взгляд
    -0.07
     bukan
    -0.07
     നന്ദ
    -0.07
    ್ತ
    -0.07
     indulge
    -0.07
    IZZ
    -0.07
    POSITIVE LOGITS
     khăn
    0.12
    ifficulty
    0.09
     impede
    0.09
     schwierig
    0.09
     moeilijk
    0.08
    難
    0.08
     어렵
    0.08
     terrains
    0.08
     dàng
    0.08
     Recall
    0.08
    Activations Density 0.088%

    No Known Activations