Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 97156
    Prev
    Next
    INDEX
    Explanations

    network

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REMOTE
    -0.09
     remotely
    -0.09
     remoto
    -0.09
     remote
    -0.09
    TOK
    -0.08
    _remote
    -0.08
     Secrets
    -0.08
    remote
    -0.08
    Remote
    -0.08
     τηλε
    -0.08
    POSITIVE LOGITS
     interception
    0.10
     interceptions
    0.10
    Timing
    0.10
    XHR
    0.10
    Interceptor
    0.09
    blocked
    0.09
     الطلب
    0.09
    Intercept
    0.09
     timings
    0.09
     intercepted
    0.09
    Activations Density 0.004%

    No Known Activations