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. 77151
    Prev
    Next
    INDEX
    Explanations

    summation

    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
     normal
    -0.09
     stereotypes
    -0.08
    agay
    -0.08
     axes
    -0.08
     looming
    -0.07
     ثق
    -0.07
     normales
    -0.07
     benchmarks
    -0.07
     interc
    -0.07
     prototypes
    -0.07
    POSITIVE LOGITS
     telesc
    0.10
     Iterable
    0.09
    Lemma
    0.08
     installment
    0.08
    umsum
    0.08
     depo
    0.08
    .iterator
    0.08
     가입
    0.08
     credited
    0.08
    Debit
    0.08
    Activations Density 0.032%

    No Known Activations