© 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. 23-RESID-POST-AA
    11. 5836
    Prev
    Next
    INDEX
    Explanations

    animated teen series dialogue

    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
     melee
    -0.07
     non
    -0.07
     gamma
    -0.07
     [
    -0.07
    inality
    -0.07
    of
    -0.07
    নি
    -0.07
     NON
    -0.06
     alternate
    -0.06
     $\
    -0.06
    POSITIVE LOGITS
     꽃
    0.09
    -collapse
    0.09
    inders
    0.08
     Butterfly
    0.08
    -feedback
    0.08
    ્બ
    0.08
    ిక్
    0.08
     Rumah
    0.08
    ిండ
    0.08
     Collapse
    0.08
    Activations Density 0.000%

    No Known Activations