© 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. 11-RESID-POST-AA
    6. 78787
    Prev
    Next
    INDEX
    Explanations

    image generation prompts

    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
     UIAlert
    -0.08
    ,length
    -0.08
     voluntarily
    -0.08
     کنترل
    -0.08
     prel
    -0.08
     vaguely
    -0.08
     aparentemente
    -0.07
     absorber
    -0.07
    egn
    -0.07
     नियंत्रण
    -0.07
    POSITIVE LOGITS
    2
    0.09
    cb
    0.09
    202
    0.09
     हूँ
    0.08
    6
    0.08
    4
    0.08
    1
    0.08
    120
    0.08
    �
    0.08
    256
    0.08
    Activations Density 0.033%

    No Known Activations