© 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. 23-RESID-POST-AA
    6. 96788
    Prev
    Next
    INDEX
    Explanations

    say ","

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flawed
    -0.09
    ලු
    -0.09
     moeilijke
    -0.09
    umweru
    -0.08
     ახალი
    -0.08
     nowe
    -0.08
     เล
    -0.08
     shabby
    -0.08
     lege
    -0.08
    _define
    -0.08
    POSITIVE LOGITS
    ,and
    0.18
     And
    0.15
    ,并
    0.14
    。そして
    0.13
    ,以及
    0.12
    —and
    0.12
    ,而且
    0.11
    And
    0.11
    "And
    0.11
    .And
    0.11
    Activations Density 0.062%

    No Known Activations