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. 46784
    Prev
    Next
    INDEX
    Explanations

    Internship reports

    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
     lune
    -0.09
     topo
    -0.08
    _literal
    -0.08
     Literal
    -0.08
     XOR
    -0.08
     ciphertext
    -0.08
     nug
    -0.07
     Broadcasting
    -0.07
     stretchy
    -0.07
    _toggle
    -0.07
    POSITIVE LOGITS
     internship
    0.18
     internships
    0.17
     Internship
    0.16
     apprenticeship
    0.14
     interns
    0.13
     trainee
    0.13
     trainees
    0.12
     учеб
    0.11
    导师
    0.11
    学习
    0.11
    Activations Density 0.041%

    No Known Activations