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. 52869
    Prev
    Next
    INDEX
    Explanations

    pandas missing data handling

    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
    yak
    -0.09
     melody
    -0.08
    ideas
    -0.08
     melodic
    -0.08
     발전
    -0.08
     ritmo
    -0.08
     muscle
    -0.08
    NASA
    -0.08
     powerhouse
    -0.08
    onik
    -0.08
    POSITIVE LOGITS
    (empty
    0.16
     Empty
    0.15
     пуст
    0.15
     empty
    0.15
     Null
    0.15
    _EMPTY
    0.14
    Empty
    0.14
     EMPTY
    0.14
     empt
    0.14
    EMPTY
    0.14
    Activations Density 0.024%

    No Known Activations