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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12379
    Prev
    Next
    INDEX
    Explanations

    social media ads

    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
    bie
    -0.08
     when
    -0.08
    াটি
    -0.08
    949
    -0.08
     Whit
    -0.08
     stimulus
    -0.07
     Ca
    -0.07
     whan
    -0.07
     sunset
    -0.07
     stimuli
    -0.07
    POSITIVE LOGITS
    _ins
    0.09
    [channel
    0.09
    审核
    0.09
    jati
    0.09
     قطر
    0.08
     enero
    0.08
    审批
    0.08
    īg
    0.08
     Ins
    0.08
    ỷ
    0.08
    Activations Density 0.001%

    No Known Activations