© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 2674
    Prev
    Next
    INDEX
    Explanations

    MMP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     σύ
    -0.09
    -wrap
    -0.07
    (&_
    -0.07
    -remove
    -0.07
     REMOVE
    -0.07
    请选择
    -0.07
    ύ
    -0.07
    -0.07
    unlink
    -0.07
    &S
    -0.07
    POSITIVE LOGITS
    Voice
    0.09
     voix
    0.08
    voice
    0.08
    Accordion
    0.08
    auks
    0.08
    VB
    0.08
     arche
    0.08
     vertr
    0.08
     takip
    0.08
    Ng
    0.08
    Activations Density 0.000%
    No Known Activations