Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 44039
    Prev
    Next
    INDEX
    Explanations

    n

    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
     MACH
    -0.09
     Mach
    -0.09
     drain
    -0.08
     modalities
    -0.08
    wm
    -0.08
    mach
    -0.08
     bolo
    -0.08
     draining
    -0.08
     voertu
    -0.07
    Mach
    -0.07
    POSITIVE LOGITS
    \Eloquent
    0.08
    Clause
    0.08
    ;x
    0.08
    丹
    0.08
    (x
    0.07
    lund
    0.07
    ਿਗ
    0.07
     Zig
    0.07
    }/{
    0.07
     Europäischen
    0.07
    Activations Density 0.006%

    No Known Activations