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. 29866
    Prev
    Next
    INDEX
    Explanations

    Date and time components

    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
    lift
    -0.08
     brill
    -0.07
    lus
    -0.07
     Ket
    -0.07
     ij
    -0.07
    akn
    -0.07
     Lj
    -0.07
    Former
    -0.07
    op
    -0.07
     Lift
    -0.07
    POSITIVE LOGITS
     haddii
    0.09
     SUBJECT
    0.09
     배우
    0.08
     sujeto
    0.08
    =value
    0.08
     процент
    0.08
    _subject
    0.08
    :value
    0.08
     BSON
    0.08
     suje
    0.08
    Activations Density 0.004%

    No Known Activations