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. 102780
    Prev
    Next
    INDEX
    Explanations

    mythology/folklore

    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
     অনুয
    -0.09
    .Bot
    -0.08
     દરમ
    -0.08
     મુજબ
    -0.08
    Snackbar
    -0.08
    ("")
    -0.08
    (Custom
    -0.08
    sprintf
    -0.08
    .Anal
    -0.08
    Intro
    -0.08
    POSITIVE LOGITS
     regal
    0.09
     символ
    0.09
    祥云
    0.09
     symbolism
    0.09
     ornate
    0.09
     adorned
    0.09
     ساق
    0.09
     золот
    0.09
     divine
    0.09
     lotus
    0.09
    Activations Density 0.015%

    No Known Activations