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. 60537
    Prev
    Next
    INDEX
    Explanations

    sometimes

    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
     emoción
    -0.08
    osmos
    -0.08
     ගැන
    -0.08
    jab
    -0.08
    OTP
    -0.08
    chat
    -0.08
    irectory
    -0.07
    kuha
    -0.07
    GPT
    -0.07
    arski
    -0.07
    POSITIVE LOGITS
     prefixes
    0.08
     fring
    0.08
     Stol
    0.08
    .variant
    0.08
     historic
    0.07
     fringe
    0.07
     enlarged
    0.07
     �
    0.07
     cnc
    0.07
     libido
    0.07
    Activations Density 0.004%

    No Known Activations