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. 90898
    Prev
    Next
    INDEX
    Explanations

    anchor and _to

    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
     murder
    -0.09
     hush
    -0.09
     hobby
    -0.09
     harmonious
    -0.09
     murderous
    -0.08
    淫
    -0.08
     Murder
    -0.08
    -pol
    -0.08
     murderer
    -0.07
     burglary
    -0.07
    POSITIVE LOGITS
    .anchor
    0.09
    Clamp
    0.09
     anch
    0.08
    (anchor
    0.08
     Anch
    0.08
     anchored
    0.08
    .Invoice
    0.07
     anchors
    0.07
     Anchor
    0.07
     dashboard
    0.07
    Activations Density 0.001%

    No Known Activations