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. 117544
    Prev
    Next
    INDEX
    Explanations

    speed

    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
     SBS
    -0.08
     Sing
    -0.07
     адбы
    -0.07
     horrifying
    -0.07
    多久
    -0.07
    laş
    -0.07
     BUS
    -0.07
     раб
    -0.07
    puta
    -0.07
     postgres
    -0.07
    POSITIVE LOGITS
     aesthetics
    0.08
     brev
    0.08
    glass
    0.07
    Tooltip
    0.07
    �
    0.07
    quent
    0.07
     aja
    0.07
     Clifford
    0.07
     vezes
    0.07
    �
    0.07
    Activations Density 0.010%

    No Known Activations