© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 102950
    Prev
    Next
    INDEX
    Explanations

    MIDI

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dangling
    -0.09
    dang
    -0.08
    _double
    -0.08
    icro
    -0.08
     towing
    -0.08
     Botswana
    -0.08
     flotation
    -0.08
     폐
    -0.08
    _FLOAT
    -0.08
     정상
    -0.07
    POSITIVE LOGITS
     MIDI
    0.29
     midi
    0.23
     Midi
    0.22
    Midi
    0.21
    -midi
    0.19
     musical
    0.19
     സംഗീത
    0.17
     musicale
    0.17
     музык
    0.17
     संगीत
    0.17
    Activations Density 0.007%

    No Known Activations