© 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. 19-RESID-POST-AA
    11. 102649
    Prev
    Next
    INDEX
    Explanations

    underscore

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Immutable
    -0.08
    .)↵
    -0.08
    ilarity
    -0.08
    ,and
    -0.08
    .But
    -0.08
     غر
    -0.07
    ımı
    -0.07
     curiosity
    -0.07
     પહોંચી
    -0.07
     مستخ
    -0.07
    POSITIVE LOGITS
    *\
    0.10
    \
    0.09
    \-
    0.09
    {}
    0.09
    ▬▬
    0.09
    \<
    0.09
    ･･
    0.09
    �
    0.09
    ><
    0.08
    �
    0.08
    Activations Density 0.002%

    No Known Activations