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. 15-RESID-POST-AA
    6. 19013
    Prev
    Next
    INDEX
    Explanations

    height

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ergic
    -0.09
    review
    -0.09
     guilt
    -0.08
    το
    -0.08
     chilling
    -0.08
    ૂબ
    -0.07
     Lia
    -0.07
    иний
    -0.07
    noch
    -0.07
    ovní
    -0.07
    POSITIVE LOGITS
    (height
    0.12
    -height
    0.12
    .Height
    0.11
     altura
    0.10
    是多少
    0.10
     Height
    0.10
     height
    0.09
    _height
    0.09
    _cm
    0.09
    .height
    0.09
    Activations Density 0.025%

    No Known Activations