© 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. 11-RESID-POST-AA
    11. 129554
    Prev
    Next
    INDEX
    Explanations

    promotion

    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
    	RTLU
    -0.09
     sages
    -0.09
     trás
    -0.08
    uhay
    -0.08
    š
    -0.08
     warranties
    -0.08
     déroule
    -0.08
     treaties
    -0.08
     اوږ
    -0.08
    ینګ
    -0.08
    POSITIVE LOGITS
    ampton
    0.08
     Furn
    0.08
    _confirm
    0.07
     quits
    0.07
     Cali
    0.07
     通
    0.07
    gateway
    0.07
    _convert
    0.07
    通
    0.07
    (Custom
    0.07
    Activations Density 0.004%

    No Known Activations